Prostate cancer (PCa) and benign prostatic hyperplasia (BPH) are significant health issues, particularly among aging male populations. Current diagnostic methods are invasive and often lack specificity, leading to unnecessary biopsies and overdiagnosis. This proposal aims to further develop a non-invasive diagnostic approach using nuclear magnetic resonance (NMR) metabolomics combined with machine learning (ML) techniques to differentiate between PCa and BPH effectively. Successful implementation of this project could revolutionize prostate health diagnostics, offering a non-invasive, reliable, and cost-effective alternative to current methods. The outcomes will include open-access scientific publications, a validated diagnostic tool, and a scalable methodology that could be applied to other types of cancers and body fluids, thereby broadening its societal impact.

2025

2026